← Back to community benchmarks

translategemma-27b-it

M5 Max (40c) · 128 GB · 8bit · 2026-03-28
Performance
16k
tokens
641.1
PP tok/s
14.9
TG tok/s
25559
TTFT (ms)
29.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.24
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 597.3 16.8 27.7 GB view
4k 645.8 15.9 28.8 GB view
8k 659.3 15.7 29.1 GB view
16k 641.1 14.9 29.7 GB current
32k 624.8 11.7 30.9 GB view
64k 590.0 7.8 33.6 GB view
Batching Results
Batch Size TG tok/s Speedup
16.8 1.00×
29.4 1.75×
39.1 2.33×
46.1 2.74×